What problem does it solve? Teams adopting AI coding agents on existing (brownfield) projects often don't know whether their current stack helps or hinders agent workflows. This Skill inspects the codebase, scores each stack component against four quality gates (typed, convention-based, popular in training data, well-documented), and produces concrete compensation strategies instead of recommending a rewrite. ## Core Features & Use Cases - Automatic stack detection: Reads project markers (package.json, Cargo.toml, pyproject.toml, go.mod, Gemfile, composer.json, *.csproj, pubspec.yaml) to identify language, framework, build tool, test runner, package manager, CI/CD, and deployment target. - Quality gate scoring with evidence: Scores each component against the four gates, citing the specific file or config that justifies every pass or fail, and assesses training-data popularity within the language family rather than globally. - Compensation strategies: For every failed gate, generates ready-to-paste CLAUDE.md/AGENTS.md rule entries so agents can work effectively despite the gap, then writes the full report to context/foundation/stack-assessment.md. - Use Case: A developer with an existing Express + JavaScript project asks whether their stack is agent-friendly. The Skill detects the stack, flags the untyped and non-convention-based gaps, and outputs concrete instruction-file rules (type annotations at boundaries, documented routing conventions) plus an overall readiness verdict. ## Quick Start Ask the agent to assess your stack by running /10x-stack-assess in your project directory, optionally passing a path to your brownfield PRD for extra context.
